The invention discloses a highway accident frequency prediction method considering time-varying features of risk factors. The method comprises the steps of 1, collecting and processing historical traffic accident data and related risk factor data; 2, establishing a Logistic regression model; 3, calculating a classification threshold value of the Logistic model by adopting a Youden index method; 4, on the basis of the Logistic model and the historical accident data, calculating a positive predictive value and a negative predictive value of the model; and 5, performing accident frequency prediction by using the positive prediction value and the negative prediction value obtained by calculation. The accident frequency prediction method can overcome the problem that a traditional accident frequency model cannot reflect the influence of the time-varying features of the risk factors on the accident, and facilitates the improvement of the prediction precision of the accident frequency prediction method.
本发明公开了一种考虑风险因素时变特征的公路事故频次预测方法,其步骤如下:1、采集和处理历史交通事故数据及相关风险因素数据;2、建立Logistic回归模型;3、采用约登指数法计算Logistic模型的分类阈值;4、基于Logistic模型和历史事故数据,计算模型的阳性预测值(Positive predictive value)和阴性预测值(Negative predictive value);5、利用计算得到的阳性预测值和阴性预测值,进行事故频次预测。本发明能克服传统事故频次模型无法反映风险因素的时变特征对事故的影响的问题,有利于提高事故频次预测方法的预测精度。
Highway accident frequency prediction method considering time-varying features of risk factors
一种考虑风险因素时变特征的公路事故频次预测方法
2021-05-25
Patent
Elektronische Ressource
Chinesisch
IPC: | G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS / G06Q Datenverarbeitungssysteme oder -verfahren, besonders angepasst an verwaltungstechnische, geschäftliche, finanzielle oder betriebswirtschaftliche Zwecke, sowie an geschäftsbezogene Überwachungs- oder Voraussagezwecke , DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES |
Navigation path optimization method considering real-time accident risk
Europäisches Patentamt | 2024
|Accident prediction model for railway-highway interfaces
Online Contents | 2006
|NTIS | 1991
NTIS | 2005
NTIS | 1995